CAJ | 학술논문

提出神经网络和数学模型相结合的方法建立太阳能集热器神经网络模型,并采用遗传算法对太阳能集热器神经网络模型进行优化,用以提高仿真模型的预测精度。在热管式真空管太阳能集热器实验数据的基础上,构建反向传输神经网络模型和遗传算法-反向传播神经网络模型,应用数学模型、反向传输神经网络模型和遗传算法-反向传播神经网络模型进行仿真计算,结果表明遗传算法-反向传播神经网络模型的计算精度高于数学模型和反向传输神经网络模型。同时该建模方法应用于太阳能集热器仿真,既提高了仿真模型的计算精度,又提高了仿真模型的通用性。
제출신경망락화수학모형상결합적방법건립태양능집열기신경망락모형,병채용유전산법대태양능집열기신경망락모형진행우화,용이제고방진모형적예측정도。재열관식진공관태양능집열기실험수거적기출상,구건반향전수신경망락모형화유전산법-반향전파신경망락모형,응용수학모형、반향전수신경망락모형화유전산법-반향전파신경망락모형진행방진계산,결과표명유전산법-반향전파신경망락모형적계산정도고우수학모형화반향전수신경망락모형。동시해건모방법응용우태양능집열기방진,기제고료방진모형적계산정도,우제고료방진모형적통용성。
The solar collector neural network model was built based on the artificial neural network and the theoretical model.Genetic algorithm was used to optimize forecast accuracy of the neural network mode.On the basis of experimental data of solar collectors,the genetic algorithm-back propagation（GA-BP） neural network model was set up.The mathematical model,the BP neural network and the GA-BP neural network model of solar collectors were used for simulation calculation.The simulation result shows that the GA-BP neural network model is more accurate than the mathematical model and the BP neural network.The application of the GA-BP neural network can improve the accuracy and versatility of the simulation model.